CloneMem:用于AI克隆的长期记忆基准测试
CloneMem: Benchmarking Long-Term Memory for AI Clones
AI总结:
CloneMem是一个用于评估AI克隆长期记忆能力的基准,通过非对话数字痕迹数据,评估代理对个人状态演变的跟踪能力。
摘要:
AI克隆旨在模拟个体的思维和行为,以实现长期的个性化交互,对内存系统提出了严格要求,以建模经历、情感和观点随时间的变化。现有内存基准主要依赖于用户代理的对话历史,这些历史是时间碎片化的,不足以捕捉连续的生活轨迹。我们引入CloneMem,一个用于评估AI克隆场景中长期记忆的基准,基于非对话的数字痕迹,包括日记、社交媒体帖子和电子邮件,时间跨度为一年至三年。CloneMem采用分层数据构建框架,以确保纵向一致性,并定义了评估代理跟踪演变个人状态能力的任务。实验显示,当前内存机制在此设置中表现不佳,突显了基于生活的真实个性化AI面临的开放挑战。代码和数据集可在https://github.com/AvatarMemory/CloneMemBench获取。
英文摘要:
AI Clones aim to simulate an individual's thoughts and behaviors to enable long-term, personalized interaction, placing stringent demands on memory systems to model experiences, emotions, and opinions over time. Existing memory benchmarks primarily rely on user-agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories. We introduce CloneMem, a benchmark for evaluating longterm memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years. CloneMem adopts a hierarchical data construction framework to ensure longitudinal coherence and defines tasks that assess an agent's ability to track evolving personal states. Experiments show that current memory mechanisms struggle in this setting, highlighting open challenges for life-grounded personalized AI. Code and dataset are available at https://github.com/AvatarMemory/CloneMemBench
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。